Yue Cao

Tsinghua University | TH · School of Software

Current object detection systems and benchmarks typically handle a limited number of categories, up to about a thousand categories. This paper scales the number of categories for object detection systems and benchmarks up to 21,000, by leveraging existing object detection and image classification data. Unlike previous efforts that usually transfer...

Frozen pretrained models have become a viable alternative to the pretraining-then-finetuning paradigm for transfer learning. However, with frozen models there are relatively few parameters available for adapting to downstream tasks, which is problematic in computer vision where tasks vary significantly in input/output format and the type of informa...

Recently, open-vocabulary image classification by vision language pre-training has demonstrated incredible achievements, that the model can classify arbitrary categories without seeing additional annotated images of that category. However, it is still unclear how to make the open-vocabulary recognition work well on broader vision problems. This pap...

Masked image modeling (MIM) learns representations with remarkably good fine-tuning performances, overshadowing previous prevalent pre-training approaches such as image classification, instance contrastive learning, and image-text alignment. In this paper, we show that the inferior fine-tuning performance of these pre-training approaches can be sig...

Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision downstream tasks, but how and where MIM works remain unclear. In this paper, we compare MIM with the long-dominant supervised pre-trained models from two perspectives, the visualizations and the experiments, to uncover their key representational differences. Fr...

Image classification, which classifies images by pre-defined categories, has been the dominant approach to visual representation learning over the last decade. Visual learning through image-text alignment, however, has emerged to show promising performance, especially for zero-shot recognition. We believe that these two learning tasks are complemen...

Recently, zero-shot image classification by vision-language pre-training has demonstrated incredible achievements, that the model can classify arbitrary category without seeing additional annotated images of that category. However, it is still unclear how to make the zero-shot recognition working well on broader vision problems, such as object dete...

This paper presents SimMIM, a simple framework for masked image modeling. We simplify recently proposed related approaches without special designs such as block-wise masking and tokenization via discrete VAE or clustering. To study what let the masked image modeling task learn good representations, we systematically study the major components in ou...

We present techniques for scaling Swin Transformer up to 3 billion parameters and making it capable of training with images of up to 1,536$\times$1,536 resolution. By scaling up capacity and resolution, Swin Transformer sets new records on four representative vision benchmarks: 84.0% top-1 accuracy on ImageNet-V2 image classification, 63.1/54.4 box...

We introduce MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free. MixTraining enhances data augmentation by utilizing augmentations of different strengths while excluding the strong augmentations of certain training samples that may be detrimental to training. In addition, it add...

The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers that globally connect patches across the spatial and temporal dimensions. In this paper, we instead advocate...

Previous cycle-consistency correspondence learning methods usually leverage image patches for training. In this paper, we present a fully convolutional method, which is simpler and more coherent to the inference process. While directly applying fully convolutional training results in model collapse, we study the underline reason behind this collaps...

We are witnessing a modeling shift from CNN to Transformers in computer vision. In this paper, we present a self-supervised learning approach called MoBY, with Vision Transformers as its backbone architecture. The approach is basically a combination of MoCo v2 and BYOL, tuned to achieve reasonably high accuracy on ImageNet-1K linear evaluation: 72....

Recently, directly detecting 3D objects from 3D point clouds has received increasing attention. To extract object representation from an irregular point cloud, existing methods usually take a point grouping step to assign the points to an object candidate so that a PointNet-like network could be used to derive object features from the grouped point...

This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two domains, such as large variations in the scale of visual entities and the high resolution of pixels in images...

The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies within an image, via aggregating query-specific global context to each query position. However, through a rigorous empirical analysis, we have found that the global contexts modeled by the non-local network are almost the same for different query posi...

The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies within an image, via aggregating query-specific global context to each query position. However, through a rigorous empirical analysis, we have found that the global contexts modeled by the non-local network are almost the same for different query posi...

Contrastive learning methods for unsupervised visual representation learning have reached remarkable levels of transfer performance. We argue that the power of contrastive learning has yet to be fully unleashed, as current methods are trained only on instance-level pretext tasks, leading to representations that may be sub-optimal for downstream tas...

Recent advances of network architecture for point cloud processing are mainly driven by new designs of local aggregation operators. However, the impact of these operators to network performance is not carefully investigated due to different overall network architecture and implementation details in each solution. Meanwhile, most of operators are on...

The non-local block is a popular module for strengthening the context modeling ability of a regular convolutional neural network. This paper first studies the non-local block in depth, where we find that its attention computation can be split into two terms, a whitened pairwise term accounting for the relationship between two pixels and a unary ter...

This paper introduces a negative margin loss to metric learning based few-shot learning methods. The negative margin loss significantly outperforms regular softmax loss, and achieves state-of-the-art accuracy on three standard few-shot classification benchmarks with few bells and whistles. These results are contrary to the common practice in the me...

Verification and regression are two general methodologies for prediction in neural networks. Each has its own strengths: verification can be easier to infer accurately, and regression is more efficient and applicable to continuous target variables. Hence, it is often beneficial to carefully combine them to take advantage of their benefits. In this...

Recent advances of network architecture for point cloud processing are mainly driven by new designs of local aggregation operators. However, the impact of these operators to network performance is not carefully investigated due to different overall network architecture and implementation details in each solution. Meanwhile, most of operators are on...

This paper presents parametric instance classification (PIC) for unsupervised visual feature learning. Unlike the state-of-the-art approaches which do instance discrimination in a dual-branch non-parametric fashion, PIC directly performs a one-branch parametric instance classification, revealing a simple framework similar to supervised classificati...

The non-local block is a popular module for strengthening the context modeling ability of a regular convolutional neural network. This paper first studies the non-local block in depth, where we find that its attention computation can be split into two terms, a whitened pairwise term accounting for the relationship between two pixels and a unary ter...

This paper introduces a negative margin loss to metric learning based few-shot learning methods. The negative margin loss significantly outperforms regular softmax loss, and achieves state-of-the-art accuracy on three standard few-shot classification benchmarks with few bells and whistles. These results are contrary to the common practice in the me...

Recent progress in multiple object tracking (MOT) has shown that a robust similarity score is key to the success of trackers. A good similarity score is expected to reflect multiple cues, e.g. appearance, location, and topology, over a long period of time. However, these cues are heterogeneous, making them hard to be combined in a unified network....

The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies, via aggregating query-specific global context to each query position. However, through a rigorous empirical analysis, we have found that the global contexts modeled by non-local network are almost the same for different query positions within an imag...

Deep hashing establishes efficient and effective image retrieval by end-to-end learning of deep representations and hash codes from similarity data. We present a compact coding solution, focusing on deep learning to quantization approach that has shown superior performance over hashing solutions for similarity retrieval. We propose Deep Triplet Qua...

Deep hashing establishes efficient and effective image retrieval by end-to-end learning of deep representations and hash codes from similarity data. We present a compact coding solution, focusing on deep learning to quantization approach that has shown superior performance over hashing solutions for similarity retrieval. We propose Deep Triplet Qua...

Cross-modal hashing enables similarity retrieval across different content modalities, such as searching relevant images in response to text queries. It provide with the advantages of computation efficiency and retrieval quality for multimedia retrieval. Hamming space retrieval enables efficient constant-time search that returns data items within a...

Domain adaptation generalizes a learning machine across source domain and target domain under different distributions. Recent studies reveal that deep neural networks can learn transferable features generalizing well to similar novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the netw...

Domain adaptation generalizes a learning model across source domain and target domain that follow different distributions. Most existing work follows a two-step procedure: first, explores either feature matching or instance reweighting independently, and second, train the transfer classifier separately. In this paper, we show that either feature ma...

Cross-modal similarity retrieval is a problem about designing a retrieval system that supports querying across content modalities, e.g., using an image to retrieve for texts. This paper presents a compact coding solution for efficient cross-modal retrieval, with a focus on the quantization approach which has already shown the superior performance o...

Approximate nearest neighbor (ANN) search is an important technique in Information Retrieval. With rapid growth of volumes of unstructured data like texts, images, and videos, how to perform efficient and accurate search from large-scale data becomes an inevitable problem. As a key approach to approximate nearest neighbor search, hashing can perfor...

Due to the storage and retrieval efficiency, hashing has been widely applied to approximate nearest neighbor search for large-scale multimedia retrieval. Cross-modal hashing, which enables efficient retrieval of images in response to text queries or vice versa, has received increasing attention recently. Most existing work on cross-modal hashing do...

Domain adaptation generalizes a learning model across source domain and target domain that are sampled from different distributions. It is widely applied to cross-domain data mining for reusing labeled information and mitigating labeling consumption. Recent studies reveal that deep neural networks can learn abstract feature representation, which ca...

Efficient similarity retrieval from large-scale multimodal database is pervasive in modern search engines and social networks. To support queries across content modalities, the system should enable cross-modal correlation and computation-efficient indexing. While hashing methods have shown great potential in achieving this goal, current attempts ge...

Due to its storage and query efficiency, hashing has been widely applied to approximate nearest neighbor search from large-scale datasets. While there is increasing interest in cross-modal hashing which facilitates cross-media retrieval by embedding data from different modalities into a common Hamming space, how to distill the cross-modal correlati...

Timestamps are often found to be dirty in various scenarios, e.g., in distributed systems with clock synchronization problems or unreliable RFID readers. Without cleaning the imprecise timestamps, temporal-related applications such as provenance analysis or pattern queries are not reliable. To evaluate the correctness of timestamps, temporal constr...

Hashing has been widely applied to approximate nearest neighbor search for large-scale multimedia retrieval. Supervised hashing improves the quality of hash coding by exploiting the semantic similarity on data pairs and has received increasing attention recently. For most existing supervised hashing methods for image retrieval, an image is first re...

Due to the storage and retrieval efficiency, hashing has been widely deployed to approximate nearest neighbor search for large-scale multimedia retrieval. Supervised hashing, which improves the quality of hash coding by exploiting the semantic similarity on data pairs, has received increasing attention recently. For most existing supervised hashing...

Due to the storage and retrieval efficiency, hashing has been widely deployed to approximate nearest neighbor search for large-scale multimedia retrieval. Cross-modal hashing, which improves the quality of hash coding by exploiting the semantic correlation across different modalities, has received increasing attention recently. For most existing cr...