ICLR 2023 Papers

Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision dictionary look-up. MIM recently dominates this line of research with state-of-the-art performance on vision Transformers (ViTs), where the core is to enhance the patch-level visual context capturing of the network via denoising auto-encoding mechanism. Rather than tailoring image tokenizers with extra training stages as in previous works, we unleash the great potential of contrastive learning on de- noising auto-encoding and introduce a pure MIM method, ConMIM, to produce simple intra-image inter-patch contrastive constraints as the sole learning objectives for masked patch prediction. We further strengthen the denoising mechanism with asymmetric designs, including image perturbations and model progress rates, to improve the network pre-training. ConMIM-pretrained models with various scales achieve competitive results on downstream image classification, semantic segmentation, object detection, and instance segmentation tasks, e.g., on ImageNet-1K classification, we achieve 83.9% top-1 accuracy with ViT-Small and 85.3% with ViT-Base without extra data for pre-training. Code will be available at https://github.com/TencentARC/ConMIM.

The \emph{stability} of learning algorithms to changes in the training sample has been actively studied as a powerful proxy for reasoning about generalization. Recently, exponential generalization and excess risk bounds with near-optimal rates have been obtained under the stringent and distribution-free notion of uniform stability~\citep{bousquet2020sharper,klochkov2021stability}. In the meanwhile, under the notion of $L_q$-stability, which is weaker and distribution dependent, exponential generalization bounds are also available yet so far only with sub-optimal rates. Therefore, a fundamental question we would like to address in this paper is whether it is possible to derive near-optimal exponential generalization bounds for $L_q$-stable learning algorithms. As the core contribution of the present work, we give an affirmative answer to this question by developing strict analogues of the near-optimal generalization and risk bounds of uniformly stable algorithms for $L_q$-stable algorithms. Further, we demonstrate the power of our improved $L_q$-stability and generalization theory by applying it to derive strong sparse excess risk bounds, under mild conditions, for computationally tractable sparsity estimation algorithms such as Iterative Hard Thresholding (IHT).

In this paper, we show that recent advances in self-supervised representation learning enable unsupervised object discovery and semantic segmentation with a performance that matches the state of the field on supervised semantic segmentation 10 years ago. We propose a methodology based on unsupervised saliency masks and self-supervised feature clustering to kickstart object discovery followed by training a semantic segmentation network on pseudo-labels to bootstrap the system on images with multiple objects. We show that while being conceptually simple our proposed baseline is surprisingly strong. We present results on PASCAL VOC that go far beyond the current state of the art (50.0 mIoU), and we report for the first time results on MS COCO for the whole set of 81 classes: our method discovers 34 categories with more than 20% IoU, while obtaining an average IoU of 19.6 for all 81 categories.

We consider fair graph representation learning via data augmentations. While this direction has been explored previously, existing methods invariably rely on certain assumptions on the properties of fair graph data in order to design fixed strategies on data augmentations. Nevertheless, the exact properties of fair graph data may vary significantly in different scenarios. Hence, heuristically designed augmentations may not always generate fair graph data in different application scenarios. In this work, we propose a method, known as Graphair, to learn fair representations based on automated graph data augmentations. Such fairness-aware augmentations are themselves learned from data. Our Graphair is designed to automatically discover fairness-aware augmentations from input graphs in order to circumvent sensitive information while preserving other useful information. Experimental results demonstrate that our Graphair consistently outperforms many baselines on multiple node classification datasets in terms of fairness-accuracy trade-off performance. In addition, results indicate that Graphair can automatically learn to generate fair graph data without prior knowledge on fairness-relevant graph properties.

Generative adversarial networks (GANs), trained on a large-scale image dataset, can be a good approximator of the natural image manifold. GAN-inversion, using a pre-trained generator as a deep generative prior, is a promising tool for image restoration under corruptions. However, the performance of GAN-inversion can be limited by a lack of robustness to unknown gross corruptions, i.e., the restored image might easily deviate from the ground truth. In this paper, we propose a Robust GAN-inversion (RGI) method with a provable robustness guarantee to achieve image restoration under unknown \textit{gross} corruptions, where a small fraction of pixels are completely corrupted. Under mild assumptions, we show that the restored image and the identified corrupted region mask converge asymptotically to the ground truth. Moreover, we extend RGI to Relaxed-RGI (R-RGI) for generator fine-tuning to mitigate the gap between the GAN learned manifold and the true image manifold while avoiding trivial overfitting to the corrupted input image, which further improves the image restoration and corrupted region mask identification performance. The proposed RGI/R-RGI method unifies two important applications with state-of-the-art (SOTA) performance: (i) mask-free semantic inpainting, where the corruptions are unknown missing regions, the restored background can be used to restore the missing content. (ii) unsupervised pixel-wise anomaly detection, where the corruptions are unknown anomalous regions, the retrieved mask can be used as the anomalous region’s segmentation mask.

Systems neuroscience relies on two complementary views of neural data, characterized by single neuron tuning curves and analysis of population activity. These two perspectives combine elegantly in neural latent variable models that constrain the relationship between latent variables and neural activity, modeled by simple tuning curve functions. This has recently been demonstrated using Gaussian processes, with applications to realistic and topologically relevant latent manifolds. Those and previous models, however, missed crucial shared coding properties of neural populations. We propose $\textit{feature sharing}$ across neural tuning curves which significantly improves performance and helps optimization. We also propose a solution to the $\textit{ensemble detection}$ problem, where different groups of neurons, i.e., ensembles, can be modulated by different latent manifolds. Achieved through a soft clustering of neurons during training, this allows for the separation of mixed neural populations in an unsupervised manner. These innovations lead to more interpretable models of neural population activity that train well and perform better even on mixtures of complex latent manifolds. Finally, we apply our method on a recently published grid cell dataset, and recover distinct ensembles, infer toroidal latents and predict neural tuning curves in a single integrated modeling framework.

Generative modelling over continuous-time geometric constructs, a.k.a $chirographic\ data$ such as handwriting, sketches, drawings etc., have been accomplished through autoregressive distributions. Such strictly-ordered discrete factorization however falls short of capturing key properties of chirographic data -- it fails to build holistic understanding of the temporal concept due to one-way visibility (causality). Consequently, temporal data has been modelled as discrete token sequences of fixed sampling rate instead of capturing the true underlying concept. In this paper, we introduce a powerful model-class namely Denoising\ Diffusion\ Probabilistic\ Models or DDPMs for chirographic data that specifically addresses these flaws. Our model named "ChiroDiff", being non-autoregressive, learns to capture holistic concepts and therefore remains resilient to higher temporal sampling rate up to a good extent. Moreover, we show that many important downstream utilities (e.g. conditional sampling, creative mixing) can be flexibly implemented using ChiroDiff. We further show some unique use-cases like stochastic vectorization, de-noising/healing, abstraction are also possible with this model-class. We perform quantitative and qualitative evaluation of our framework on relevant datasets and found it to be better or on par with competing approaches.

Chain-of-thought prompting combined with pretrained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the naive greedy decoding used in chain-of-thought prompting. It first samples a diverse set of reasoning paths instead of only taking the greedy one, and then selects the most consistent answer by marginalizing out all possible reasoning paths. Self-consistency leverages the intuition that a complex reasoning problem typically admits multiple different ways of thinking leading to its unique correct answer. Our extensive empirical evaluation shows that self-consistency boosts the performance of chain-of-thought prompting with a striking margin on a range of popular arithmetic and commonsense reasoning benchmarks, including GSM8K (+17.9%), SVAMP (+11.0%), AQuA (+12.2%), StrategyQA (+6.4%) and ARC-challenge (+3.9%).

Deformable object manipulation (DOM) is a long-standing challenge in robotics and has attracted significant interest recently. This paper presents DaXBench, a differentiable simulation framework for DOM. While existing work often focuses on a specific type of deformable objects, DaXBench supports fluid, rope, cloth ...; it provides a general-purpose benchmark to evaluate widely different DOM methods, including planning, imitation learning, and reinforcement learning. DaXBench combines recent advances in deformable object simulation with JAX, a high-performance computational framework. All DOM tasks in DaXBench are wrapped with the OpenAI Gym API for easy integration with DOM algorithms. We hope that DaXBench provides to the research community a comprehensive, standardized benchmark and a valuable tool to support the development and evaluation of new DOM methods. The code and video are available online.

We propose topology-aware feature partitioning into $k$ disjoint partitions for given scene features as a method for object-centric representation learning. To this end, we propose to use minimum $s$-$t$ graph cuts as a partitioning method which is represented as a linear program. The method is topologically aware since it explicitly encodes neighborhood relationships in the image graph. To solve the graph cuts our solution relies on an efficient, scalable, and differentiable quadratic programming approximation. Optimizations specific to cut problems allow us to solve the quadratic programs and compute their gradients significantly more efficiently compared with the general quadratic programming approach. Our results show that our approach is scalable and outperforms existing methods on object discovery tasks with textured scenes and objects.

Today, ground-truth generation uses data sets annotated by cloud-based annotation services. These services rely on human annotation, which can be prohibitively expensive. In this paper, we consider the problem of hybrid human-machine labeling, which trains a classifier to accurately auto-label part of the data set. However, training the classifier can be expensive too. We propose an iterative approach that minimizes total overall cost by, at each step, jointly determining which samples to label using humans and which to label using the trained classifier. We validate our approach on well known public data sets such as Fashion-MNIST, CIFAR-10, CIFAR-100, and ImageNet. In some cases, our approach has 6× lower overall cost relative to human labeling the entire data set, and is always cheaper than the cheapest competing strategy.

We introduce STREET, a unified multi-task and multi-domain natural language reasoning and explanation benchmark. Unlike most existing question-answering (QA) datasets, we expect models to not only answer questions, but also produce step-by-step structured explanations describing how premises in the question are used to produce intermediate conclusions that can prove the correctness of a certain answer. We perform extensive evaluation with popular language models such as few-shot prompting GPT-3 and fine-tuned T5. We find that these models still lag behind human performance when producing such structured reasoning steps. We believe this work will provide a way for the community to better train and test systems on multi-step reasoning and explanations in natural language.

Physically rearranging objects is an important capability for embodied agents. Visual room rearrangement evaluates an agent's ability to rearrange objects in a room to a desired goal based solely on visual input. We propose a simple yet effective method for this problem: (1) search for and map which objects need to be rearranged, and (2) rearrange each object until the task is complete. Our approach consists of an off-the-shelf semantic segmentation model, voxel-based semantic map, and semantic search policy to efficiently find objects that need to be rearranged. Our method was the winning submission to the AI2-THOR Rearrangement Challenge in the 2022 Embodied AI Workshop at CVPR 2022, and improves on current state-of-the-art end-to-end reinforcement learning-based methods that learn visual room rearrangement policies from 0.53% correct rearrangement to 16.56%, using only 2.7% as many samples from the environment.

Task-free continual learning is the machine-learning setting where a model is trained online with data generated by a nonstationary stream. Conventional wisdom suggests that, in this setting, models are trained using an approach called experience replay, where the risk is computed both with respect to current stream observations and to a small subset of past observations. In this work, we explain both theoretically and empirically how experience replay biases the outputs of the model towards recent stream observations. Moreover, we propose a simple approach to mitigate this bias online, by changing how the output layer of the model is optimized. We show that our approach improves significantly the learning performance of experience-replay approaches over different datasets. Our findings suggest that, when performing experience replay, the output layer of the model should be optimized separately from the preceding layers.

Deep reinforcement learning algorithms that learn policies by trial-and-error must learn from limited amounts of data collected by actively interacting with the environment. While many prior works have shown that proper regularization techniques are crucial for enabling data-efficient RL, a general understanding of the bottlenecks in data-efficient RL has remained unclear. Consequently, it has been difficult to devise a universal technique that works well across all domains. In this paper, we attempt to understand the primary bottleneck in sample-efficient deep RL by examining several potential hypotheses such as non-stationarity, excessive action distribution shift, and overfitting. We perform thorough empirical analysis on state-based DeepMind control suite (DMC) tasks in a controlled and systematic way to show that high temporal-difference (TD) error on the validation set of transitions is the main culprit that severely affects the performance of deep RL algorithms, and prior methods that lead to good performance do in fact, control the validation TD error to be low. This observation gives us a robust principle for making deep RL efficient: we can hill-climb on the validation TD error by utilizing any form of regularization techniques from supervised learning. We show that a simple online model selection method that targets the validation TD error is effective across state-based DMC and Gym tasks.

Reward design in reinforcement learning (RL) is challenging since specifying human notions of desired behavior may be difficult via reward functions or require many expert demonstrations. Can we instead cheaply design rewards using a natural language interface? This paper explores how to simplify reward design by using a large language model (LLM) such as GPT-3 as a proxy reward function, where the user provides a textual prompt containing a few examples (few-shot) or a description (zero-shot) of desired behavior. Our approach leverages this proxy reward function in an RL framework. Specifically, users specify a prompt once at the beginning of training. During training, the LLM evaluates an RL agent's behavior against the desired behavior described by the prompt and outputs a corresponding reward signal. The RL agent then uses this reward to update its behavior. We evaluate whether our approach can train agents aligned with user objectives in the Ultimatum Game, matrix games, and the DealOrNoDeal negotiation task. In all three tasks, we show that RL agents trained with our framework are well-aligned with the user's objectives and outperforms RL agents trained with reward functions learned via supervised learning.

We propose ADCLR: \underline{A}ccurate and \underline{D}ense \underline{C}ontrastive \underline{R}epresentation \underline{L}earning, a novel self-supervised learning framework for learning accurate and dense vision representation. To extract spatial-sensitive information, ADCLR introduces query patches for contrasting in addition with global contrasting. Compared with previous dense contrasting methods, ADCLR mainly enjoys three merits: i) achieving both global-discriminative and spatial-sensitive representation, ii) model-efficient (no extra parameters in addition to the global contrasting baseline), and iii) correspondence-free and thus simpler to implement. Our approach achieves new state-of-the-art performance for contrastive methods. On classification tasks, for ViT-S, ADCLR achieves 78.1\% top-1 accuracy on ImageNet with linear probing, outperforming our baseline (DINO) without our devised techniques as plug-in, by 1.1\%. For ViT-B, ADCLR achieves 79.8\%, 84.0\% accuracy on ImageNet by linear probing and finetune, outperforming DINO by 0.6\%, 0.4\% accuracy. For dense tasks, on MS-COCO, ADCLR achieves significant improvements of 44.3\% AP on object detection, 39.7\% AP on instance segmentation, outperforming previous SOTA method SelfPatch by 2.2\% and 1.2\%, respectively. On ADE20K, ADCLR outperforms SelfPatch by 1.0\% mIoU, 1.2\% mAcc on the segmentation task.

Diffusion probabilistic models (DPMs) have become a popular approach to conditional generation, due to their promising results and support for cross-modal synthesis. A key desideratum in conditional synthesis is to achieve high correspondence between the conditioning input and generated output. Most existing methods learn such relationships implicitly, by incorporating the prior into the variational lower bound. In this work, we take a different route---we explicitly enhance input-output connections by maximizing their mutual information. To this end, we introduce a Conditional Discrete Contrastive Diffusion (CDCD) loss and design two contrastive diffusion mechanisms to effectively incorporate it into the denoising process, combining the diffusion training and contrastive learning for the first time by connecting it with the conventional variational objectives. We demonstrate the efficacy of our approach in evaluations with diverse multimodal conditional synthesis tasks: dance-to-music generation, text-to-image synthesis, as well as class-conditioned image synthesis. On each, we enhance the input-output correspondence and achieve higher or competitive general synthesis quality. Furthermore, the proposed approach improves the convergence of diffusion models, reducing the number of required diffusion steps by more than 35% on two benchmarks, significantly increasing the inference speed.

We address the task of view synthesis, generating novel views of a scene given a set of images as input. In many recent works such as NeRF (Mildenhall et al., 2020), the scene geometry is parameterized using neural implicit representations (i.e., MLPs). Implicit neural representations have achieved impressive visual quality but have drawbacks in computational efficiency. In this work, we propose a new approach that performs view synthesis using point clouds. It is the first point-based method that achieves better visual quality than NeRF while being 100× faster in rendering speed. Our approach builds on existing works on differentiable point-based rendering but introduces a novel technique we call “Sculpted Neural Points (SNP)”, which significantly improves the robustness to errors and holes in the reconstructed point cloud. We further propose to use view-dependent point features based on spherical harmonics to capture non-Lambertian surfaces, and new designs in the point-based rendering pipeline that further boost the performance. Finally, we show that our system supports fine-grained scene editing. Code is available at https://github.com/princeton-vl/SNP.