Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We introduce, ResFormer, a framework that is built upon the seminal idea of multi-resolution training for improved performance on a wide spectrum of, mostly unseen, testing resolutions. In particular, ResFormer operates on replicated images of different resolutions and enforces a scale consistency loss to engage interactive information across different scales. More importantly, to alternate among varying resolutions, we propose a global-local positional embedding strategy that changes smoothly conditioned on input sizes. This allows ResFormer to cope with novel resolutions effectively. We conduct extensive experiments for image classification on ImageNet. The results provide strong quantitative evidence that ResFormer has promising scaling abilities towards a wide range resolutions. For instance, ResFormer-B-MR achieves a Top-1 accuracy of 75.86% and 81.72% when evaluated on relatively low and high resolutions respectively (i.e., 96 and 640), which are 48% and 7.49% better than DeiT-B. We also demonstrate, among other things, ResFormer is flexible and can be easily extended to semantic segmentation and video action recognition.
Semi-supervised action recognition is a challenging but critical task due to the high cost of video annotations. Existing approaches mainly use convolutional neural networks, yet current revolutionary vision transformer models have been less explored. In this paper, we investigate the use of transformer models under the SSL setting for action recognition. To this end, we introduce SVFormer, which adopts a steady pseudo-labeling framework (ie, EMA-Teacher) to cope with unlabeled video samples. While a wide range of data augmentations have been shown effective for semi-supervised image classification, they generally produce limited results for video recognition. We therefore introduce a novel augmentation strategy, Tube TokenMix, tailored for video data where video clips are mixed via a mask with consistent masked tokens over the temporal axis. In addition, we propose a temporal warping augmentation to cover the complex temporal variation in videos, which stretches selected frames to various temporal durations in the clip. Extensive experiments on three datasets Kinetics-400, UCF-101, and HMDB-51 verify the advantage of SVFormer. In particular, SVFormer outperforms the state-of-the-art by 31.5% with fewer training epochs under the 1% labeling rate of Kinetics-400. Our method can hopefully serve as a strong benchmark and encourage future search on semi-supervised action recognition with Transformer networks.
The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one. We present a diffusion-based captioning model, dubbed the name DDCap, to allow more decoding flexibility. Unlike image generation, where the output is continuous and redundant with a fixed length, texts in image captions are categorical and short with varied lengths. Therefore, naively applying the discrete diffusion model to text decoding does not work well, as shown in our experiments. To address the performance gap, we propose several key techniques including best-first inference, concentrated attention mask, text length prediction, and image-free training. On COCO without additional caption pre-training, it achieves a CIDEr score of 117.8, which is +5.0 higher than the auto-regressive baseline with the same architecture in the controlled setting. It also performs +26.8 higher CIDEr score than the auto-regressive baseline (230.3 v.s.203.5) on a caption infilling task. With 4M vision-language pre-training images and the base-sized model, we reach a CIDEr score of 125.1 on COCO, which is competitive to the best well-developed auto-regressive frameworks. The code is available at https://github.com/buxiangzhiren/DDCap.
Image cropping has progressed tremendously under the data-driven paradigm. However, current approaches do not account for the intentions of the user, which is an issue especially when the composition of the input image is complex. Moreover, labeling of cropping data is costly and hence the amount of data is limited, leading to poor generalization performance of current algorithms in the wild. In this work, we take advantage of vision-language models as a foundation for creating robust and user-intentional cropping algorithms. By adapting a transformer decoder with a pre-trained CLIP-based detection model, OWL-ViT, we develop a method to perform cropping with a text or image query that reflects the user's intention as guidance. In addition, our pipeline design allows the model to learn text-conditioned aesthetic cropping with a small cropping dataset, while inheriting the open-vocabulary ability acquired from millions of text-image pairs. We validate our model through extensive experiments on existing datasets as well as a new cropping test set we compiled that is characterized by content ambiguity.
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 information that is of value. In this paper, we present a study of frozen pretrained models when applied to diverse and representative computer vision tasks, including object detection, semantic segmentation and video action recognition. From this empirical analysis, our work answers the questions of what pretraining task fits best with this frozen setting, how to make the frozen setting more flexible to various downstream tasks, and the effect of larger model sizes. We additionally examine the upper bound of performance using a giant frozen pretrained model with 3 billion parameters (SwinV2-G) and find that it reaches competitive performance on a varied set of major benchmarks with only one shared frozen base network: 60.0 box mAP and 52.2 mask mAP on COCO object detection test-dev, 57.6 val mIoU on ADE20K semantic segmentation, and 81.7 top-1 accuracy on Kinetics-400 action recognition. With this work, we hope to bring greater attention to this promising path of freezing pretrained image models.
Vision transformers have recently achieved competitive results across various vision tasks but still suffer from heavy computation costs when processing a large number of tokens. Many advanced approaches have been developed to reduce the total number of tokens in large-scale vision transformers, especially for image classification tasks. Typically, they select a small group of essential tokens according to their relevance with the class token, then fine-tune the weights of the vision transformer. Such fine-tuning is less practical for dense prediction due to the much heavier computation and GPU memory cost than image classification. In this paper, we focus on a more challenging problem, i.e., accelerating large-scale vision transformers for dense prediction without any additional re-training or fine-tuning. In response to the fact that high-resolution representations are necessary for dense prediction, we present two non-parametric operators, a token clustering layer to decrease the number of tokens and a token reconstruction layer to increase the number of tokens. The following steps are performed to achieve this: (i) we use the token clustering layer to cluster the neighboring tokens together, resulting in low-resolution representations that maintain the spatial structures; (ii) we apply the following transformer layers only to these low-resolution representations or clustered tokens; and (iii) we use the token reconstruction layer to re-create the high-resolution representations from the refined low-resolution representations. The results obtained by our method are promising on five dense prediction tasks, including object detection, semantic segmentation, panoptic segmentation, instance segmentation, and depth estimation.
Semantic communication in the 6G era has been deemed a promising communication paradigm to break through the bottleneck of traditional communications. However, its applications for the multi-user scenario, especially the broadcasting case, remain under-explored. To effectively exploit the benefits enabled by semantic communication, in this paper, we propose a one-to-many semantic communication system. Specifically, we propose a deep neural network (DNN) enabled semantic communication system called MR\_DeepSC. By leveraging semantic features for different users, a semantic recognizer based on the pre-trained model, i.e., DistilBERT, is built to distinguish different users. Furthermore, the transfer learning is adopted to speed up the training of new receiver networks. Simulation results demonstrate that the proposed MR\_DeepSC can achieve the best performance in terms of BLEU score than the other benchmarks under different channel conditions, especially in the low signal-to-noise ratio (SNR) regime.
Few-shot visual recognition refers to recognize novel visual concepts from a few labeled instances. Many few-shot visual recognition methods adopt the metric-based meta-learning paradigm by comparing the query representation with class representations to predict the category of query instance. However, current metric-based methods generally treat all instances equally and consequently often obtain biased class representation, considering not all instances are equally significant when summarizing the instance-level representations for the class-level representation. For example, some instances may contain unrepresentative information, such as too much background and information of unrelated concepts, which skew the results. To address the above issues, we propose a novel metric-based meta-learning framework termed instance-adaptive class representation learning network (ICRL-Net) for few-shot visual recognition. Specifically, we develop an adaptive instance revaluing network with the capability to address the biased representation issue when generating the class representation, by learning and assigning adaptive weights for different instances according to their relative significance in the support set of corresponding class. Additionally, we design an improved bilinear instance representation and incorporate two novel structural losses, i.e., intra-class instance clustering loss and inter-class representation distinguishing loss, to further regulate the instance revaluation process and refine the class representation. We conduct extensive experiments on four commonly adopted few-shot benchmarks: miniImageNet, tieredImageNet, CIFAR-FS, and FC100 datasets. The experimental results compared with the state-of-the-art approaches demonstrate the superiority of our ICRL-Net.
Few-shot part segmentation aims to separate different parts of an object given only a few annotated samples. Due to the challenge of limited data, existing works mainly focus on learning classifiers over pre-trained features, failing to learn task-specific features for part segmentation. In this paper, we propose to learn task-specific features in a "pre-training"-"fine-tuning" paradigm. We conduct prompt designing to reduce the gap between the pre-train task (i.e., image generation) and the downstream task (i.e., part segmentation), so that the GAN priors for generation can be leveraged for segmentation. This is achieved by projecting part segmentation maps into the RGB space and conducting interpolation between RGB segmentation maps and original images. Specifically, we design a fine-tuning strategy to progressively tune an image generator into a segmentation generator, where the supervision of the generator varying from images to segmentation maps by interpolation. Moreover, we propose a two-stream architecture, i.e., a segmentation stream to generate task-specific features, and an image stream to provide spatial constraints. The image stream can be regarded as a self-supervised auto-encoder, and this enables our model to benefit from large-scale support images. Overall, this work is an attempt to explore the internal relevance between generation tasks and perception tasks by prompt designing. Extensive experiments show that our model can achieve state-of-the-art performance on several part segmentation datasets.
One-to-one set matching is a key design for DETR to establish its end-to-end capability, so that object detection does not require a hand-crafted NMS (non-maximum suppression) method to remove duplicate detections. This end-to-end signature is important for the versatility of DETR, and it has been generalized to a wide range of visual problems, including instance/semantic segmentation, human pose estimation, and point cloud/multi-view-images based detection, etc. However, we note that because there are too few queries assigned as positive samples, the one-to-one set matching significantly reduces the training efficiency of positive samples. This paper proposes a simple yet effective method based on a hybrid matching scheme that combines the original one-to-one matching branch with auxiliary queries that use one-to-many matching loss during training. This hybrid strategy has been shown to significantly improve training efficiency and improve accuracy. In inference, only the original one-to-one match branch is used, thus maintaining the end-to-end merit and the same inference efficiency of DETR. The method is named $\mathcal{H}$-DETR, and it shows that a wide range of representative DETR methods can be consistently improved across a wide range of visual tasks, including Deformable-DETR, 3DETR/PETRv2, PETR, and TransTrack, among others. Code will be available at: https://github.com/HDETR