In this paper, we introduce YONOS-SR, a novel stable diffusion-based approach for image super-resolution that yields state-of-the-art results using only a single DDIM step. We propose a novel scale distillation approach to train our SR model. Instead of directly training our SR model on the scale factor of interest, we start by training a teacher model on a smaller magnification scale, thereby making the SR problem simpler for the teacher. We then train a student model for a higher magnification scale, using the predictions of the teacher as a target during the training. This process is repeated iteratively until we reach the target scale factor of the final model. The rationale behind our scale distillation is that the teacher aids the student diffusion model training by i) providing a target adapted to the current noise level rather than using the same target coming from ground truth data for all noise levels and ii) providing an accurate target as the teacher has a simpler task to solve. We empirically show that the distilled model significantly outperforms the model trained for high scales directly, specifically with few steps during inference. Having a strong diffusion model that requires only one step allows us to freeze the U-Net and fine-tune the decoder on top of it. We show that the combination of spatially distilled U-Net and fine-tuned decoder outperforms state-of-the-art methods requiring 200 steps with only one single step.
DETR-based object detectors have achieved remarkable performance but are sample-inefficient and exhibit slow convergence. Unsupervised pretraining has been found to be helpful to alleviate these impediments, allowing training with large amounts of unlabeled data to improve the detector's performance. However, existing methods have their own limitations, like keeping the detector's backbone frozen in order to avoid performance degradation and utilizing pretraining objectives misaligned with the downstream task. To overcome these limitations, we propose a simple pretraining framework for DETR-based detectors that consists of three simple yet key ingredients: (i) richer, semantics-based initial proposals derived from high-level feature maps, (ii) discriminative training using object pseudo-labels produced via clustering, (iii) self-training to take advantage of the improved object proposals learned by the detector. We report two main findings: (1) Our pretraining outperforms prior DETR pretraining works on both the full and low data regimes by significant margins. (2) We show we can pretrain DETR from scratch (including the backbone) directly on complex image datasets like COCO, paving the path for unsupervised representation learning directly using DETR.
Vision-Language (V-L) models trained with contrastive learning to align the visual and language modalities have been shown to be strong few-shot learners. Soft prompt learning is the method of choice for few-shot downstream adaption aiming to bridge the modality gap caused by the distribution shift induced by the new domain. While parameter-efficient, prompt learning still requires access to the model weights and can be computationally infeasible for large models with billions of parameters. To address these shortcomings, in this work, we describe a black-box method for V-L few-shot adaptation that (a) operates on pre-computed image and text features and hence works without access to the model's weights, (b) it is orders of magnitude faster at training time, (c) it is amenable to both supervised and unsupervised training, and (d) it can be even used to align image and text features computed from uni-modal models. To achieve this, we propose Linear Feature Alignment (LFA), a simple linear approach for V-L re-alignment in the target domain. LFA is initialized from a closed-form solution to a least-squares problem and then it is iteratively updated by minimizing a re-ranking loss. Despite its simplicity, our approach can even surpass soft-prompt learning methods as shown by extensive experiments on 11 image and 2 video datasets.
This paper is on Few-Shot Object Detection (FSOD), where given a few templates (examples) depicting a novel class (not seen during training), the goal is to detect all of its occurrences within a set of images. From a practical perspective, an FSOD system must fulfil the following desiderata: (a) it must be used as is, without requiring any fine-tuning at test time, (b) it must be able to process an arbitrary number of novel objects concurrently while supporting an arbitrary number of examples from each class and (c) it must achieve accuracy comparable to a closed system. While there are (relatively) few systems that support (a), to our knowledge, there is no system supporting (b) and (c). In this work, we make the following contributions: We introduce, for the first time, a simple, yet powerful, few-shot detection transformer (FS-DETR) that can address both desiderata (a) and (b). Our system builds upon the DETR framework, extending it based on two key ideas: (1) feed the provided visual templates of the novel classes as visual prompts during test time, and (2) ``stamp'' these prompts with pseudo-class embeddings, which are then predicted at the output of the decoder. Importantly, we show that our system is not only more flexible than existing methods, but also, making a step towards satisfying desideratum (c), it is more accurate, matching and outperforming the current state-of-the-art on the most well-established benchmarks (PASCAL VOC & MSCOCO) for FSOD. Code will be made available.
Prompt tuning provides an efficient mechanism to adapt large vision-language models to downstream tasks by treating part of the input language prompts as learnable parameters while freezing the rest of the model. Existing works for prompt tuning are however prone to damaging the generalization capabilities of the foundation models, because the learned prompts lack the capacity of covering certain concepts within the language model. To avoid such limitation, we propose a probabilistic modeling of the underlying distribution of prompts, allowing prompts within the support of an associated concept to be derived through stochastic sampling. This results in a more complete and richer transfer of the information captured by the language model, providing better generalization capabilities for downstream tasks. The resulting algorithm relies on a simple yet powerful variational framework that can be directly integrated with other developments. We show our approach is seamlessly integrated into both standard and conditional prompt learning frameworks, improving the performance on both cases considerably, especially with regards to preserving the generalization capability of the original model. Our method provides the current state-of-the-art for prompt learning, surpassing CoCoOp by 1.6% average Top-1 accuracy on the standard benchmark. Remarkably, it even surpasses the original CLIP model in terms of generalization to new classes. Implementation code will be released.
This paper is on soft prompt learning for Vision \& Language (V&L) models. Similarly to their NLP counterparts, V\&L models can be adapted to a downstream task by learning soft continuous prompts using a few training examples. Current methods learn the soft prompts by minimizing a cross-entropy loss using as class weights the features obtained by passing the prompts plus the class names through the text encoder. Such methods, however, significantly overfit the training data suffering from large accuracy degradation when tested on unseen classes from the same domain. Our main contribution, in this paper, is a surprisingly simple approach to alleviate this problem: we use a second cross entropy loss to minimize the distance between the learned soft prompts and a set of hand-engineered manual prompts (obtained by prompt engineering). The proposed loss can be interpreted in multiple ways including as a regularizer, as a means for language-based augmentation, and as a way of learning more discriminative class centroids. Importantly, our formulation is inherently amenable to including, during training, virtual classes, i.e. class names for which no visual samples are available, further increasing the robustness of the learned prompts. Through extensive evaluations on 11 datasets, we show that our approach (a) significantly outperforms all prior works on soft prompting, and (b) matches and surpasses, for the first time, the accuracy on novel classes obtained by hand-crafted prompts and CLIP for the majority of the test datasets. Code will be made available.
This work is on training a generative action/video recognition model whose output is a free-form action-specific caption describing the video (rather than an action class label). A generative approach has practical advantages like producing more fine-grained and human-readable output, and being naturally open-world. To this end, we propose to adapt a pre-trained generative Vision & Language (V&L) Foundation Model for video/action recognition. While recently there have been a few attempts to adapt V&L models trained with contrastive learning (e.g. CLIP) for video/action, to the best of our knowledge, we propose the very first method that sets outs to accomplish this goal for a generative model. We firstly show that direct fine-tuning of a generative model to produce action classes suffers from severe overfitting. To alleviate this, we introduce REST, a training framework consisting of two key components: an unsupervised method for adapting the generative model to action/video by means of pseudo-caption generation and Self-training, i.e. without using any action-specific labels; (b) a Retrieval approach based on CLIP for discovering a diverse set of pseudo-captions for each video to train the model. Importantly, we show that both components are necessary to obtain high accuracy. We evaluate REST on the problem of zero-shot action recognition where we show that our approach is very competitive when compared to contrastive learning-based methods. Code will be made available.
This paper tackles the problem of efficient video recognition. In this area, video transformers have recently dominated the efficiency (top-1 accuracy vs FLOPs) spectrum. At the same time, there have been some attempts in the image domain which challenge the necessity of the self-attention operation within the transformer architecture, advocating the use of simpler approaches for token mixing. However, there are no results yet for the case of video recognition, where the self-attention operator has a significantly higher impact (compared to the case of images) on efficiency. To address this gap, in this paper, we make the following contributions: (a) we construct a highly efficient \& accurate attention-free block based on the shift operator, coined Affine-Shift block, specifically designed to approximate as closely as possible the operations in the MHSA block of a Transformer layer. Based on our Affine-Shift block, we construct our Affine-Shift Transformer and show that it already outperforms all existing shift/MLP--based architectures for ImageNet classification. (b) We extend our formulation in the video domain to construct Video Affine-Shift Transformer (VAST), the very first purely attention-free shift-based video transformer. (c) We show that VAST significantly outperforms recent state-of-the-art transformers on the most popular action recognition benchmarks for the case of models with low computational and memory footprint. Code will be made available.
Learning visual representations through self-supervision is an extremely challenging task as the network needs to sieve relevant patterns from spurious distractors without the active guidance provided by supervision. This is achieved through heavy data augmentation, large-scale datasets and prohibitive amounts of compute. Video self-supervised learning (SSL) suffers from added challenges: video datasets are typically not as large as image datasets, compute is an order of magnitude larger, and the amount of spurious patterns the optimizer has to sieve through is multiplied several fold. Thus, directly learning self-supervised representations from video data might result in sub-optimal performance. To address this, we propose to utilize a strong image-based model, pre-trained with self- or language supervision, in a video representation learning framework, enabling the model to learn strong spatial and temporal information without relying on the video labeled data. To this end, we modify the typical video-based SSL design and objective to encourage the video encoder to \textit{subsume} the semantic content of an image-based model trained on a general domain. The proposed algorithm is shown to learn much more efficiently (i.e. in less epochs and with a smaller batch) and results in a new state-of-the-art performance on standard downstream tasks among single-modality SSL methods.
Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is largely overlooked. In this work, we propose a novel {\em \modelname{}} ({\bf\em \shortname{})} method dedicated for distilling representational knowledge semantically from a pretrained teacher to a target student. The key idea is that we leverage the teacher's classifier as a semantic critic for evaluating the representations of both teacher and student and distilling the semantic knowledge with high-order structured information over all feature dimensions. This is accomplished by introducing a notion of cross-network logit computed through passing student's representation into teacher's classifier. Further, considering the set of seen classes as a basis for the semantic space in a combinatorial perspective, we scale \shortname{} to unseen classes for enabling effective exploitation of largely available, arbitrary unlabeled training data. At the problem level, this establishes an interesting connection between knowledge distillation with open-set semi-supervised learning (SSL). Extensive experiments show that our \shortname{} outperforms significantly previous state-of-the-art knowledge distillation methods on both coarse object classification and fine face recognition tasks, as well as less studied yet practically crucial binary network distillation. Under more realistic open-set SSL settings we introduce, we reveal that knowledge distillation is generally more effective than existing Out-Of-Distribution (OOD) sample detection, and our proposed \shortname{} is superior over both previous distillation and SSL competitors. The source code is available at \url{https://github.com/jingyang2017/SRD\_ossl}.