Large pre-trained models such as CLIP offer consistent accuracy across a range of data distributions when performing zero-shot inference (i.e., without fine-tuning on a specific dataset). Although existing fine-tuning approaches substantially improve accuracy in-distribution, they also reduce out-of-distribution robustness. We address this tension by introducing a simple and effective method for improving robustness: ensembling the weights of the zero-shot and fine-tuned models. Compared to standard fine-tuning, the resulting weight-space ensembles provide large accuracy improvements out-of-distribution, while matching or improving in-distribution accuracy. On ImageNet and five derived distribution shifts, weight-space ensembles improve out-of-distribution accuracy by 2 to 10 percentage points while increasing in-distribution accuracy by nearly 1 percentage point relative to standard fine-tuning. These improvements come at no additional computational cost during fine-tuning or inference.
To realize robots that can understand human instructions and perform meaningful tasks in the near future, it is important to develop learned models that can understand referential language to identify common objects in real-world 3D scenes. In this paper, we develop a spatial-language model for a 3D visual grounding problem. Specifically, given a reconstructed 3D scene in the form of a point cloud with 3D bounding boxes of potential object candidates, and a language utterance referring to a target object in the scene, our model identifies the target object from a set of potential candidates. Our spatial-language model uses a transformer-based architecture that combines spatial embedding from bounding-box with a finetuned language embedding from DistilBert and reasons among the objects in the 3D scene to find the target object. We show that our model performs competitively on visio-linguistic datasets proposed by ReferIt3D. We provide additional analysis of performance in spatial reasoning tasks decoupled from perception noise, the effect of view-dependent utterances in terms of accuracy, and view-point annotations for potential robotics applications.
As humans, we understand events in the visual world contextually, performing multimodal reasoning across time to make inferences about the past, present, and future. We introduce MERLOT, a model that learns multimodal script knowledge by watching millions of YouTube videos with transcribed speech -- in an entirely label-free, self-supervised manner. By pretraining with a mix of both frame-level (spatial) and video-level (temporal) objectives, our model not only learns to match images to temporally corresponding words, but also to contextualize what is happening globally over time. As a result, MERLOT exhibits strong out-of-the-box representations of temporal commonsense, and achieves state-of-the-art performance on 12 different video QA datasets when finetuned. It also transfers well to the world of static images, allowing models to reason about the dynamic context behind visual scenes. On Visual Commonsense Reasoning, MERLOT answers questions correctly with 80.6% accuracy, outperforming state-of-the-art models of similar size by over 3%, even those that make heavy use of auxiliary supervised data (like object bounding boxes). Ablation analyses demonstrate the complementary importance of: 1) training on videos versus static images; 2) scaling the magnitude and diversity of the pretraining video corpus; and 3) using diverse objectives that encourage full-stack multimodal reasoning, from the recognition to cognition level.
Learning binary representations of instances and classes is a classical problem with several high potential applications. In modern settings, the compression of high-dimensional neural representations to low-dimensional binary codes is a challenging task and often require large bit-codes to be accurate. In this work, we propose a novel method for Learning Low-dimensional binary Codes (LLC) for instances as well as classes. Our method does not require any side-information, like annotated attributes or label meta-data, and learns extremely low-dimensional binary codes (~20 bits for ImageNet-1K). The learnt codes are super-efficient while still ensuring nearly optimal classification accuracy for ResNet50 on ImageNet-1K. We demonstrate that the learnt codes capture intrinsically important features in the data, by discovering an intuitive taxonomy over classes. We further quantitatively measure the quality of our codes by applying it to the efficient image retrieval as well as out-of-distribution (OOD) detection problems. For ImageNet-100 retrieval problem, our learnt binary codes outperform 16 bit HashNet using only 10 bits and also are as accurate as 10 dimensional real representations. Finally, our learnt binary codes can perform OOD detection, out-of-the-box, as accurately as a baseline that needs ~3000 samples to tune its threshold, while we require none. Code and pre-trained models are available at https://github.com/RAIVNLab/LLC.
We propose PIGLeT: a model that learns physical commonsense knowledge through interaction, and then uses this knowledge to ground language. We factorize PIGLeT into a physical dynamics model, and a separate language model. Our dynamics model learns not just what objects are but also what they do: glass cups break when thrown, plastic ones don't. We then use it as the interface to our language model, giving us a unified model of linguistic form and grounded meaning. PIGLeT can read a sentence, simulate neurally what might happen next, and then communicate that result through a literal symbolic representation, or natural language. Experimental results show that our model effectively learns world dynamics, along with how to communicate them. It is able to correctly forecast "what happens next" given an English sentence over 80% of the time, outperforming a 100x larger, text-to-text approach by over 10%. Likewise, its natural language summaries of physical interactions are also judged by humans as more accurate than LM alternatives. We present comprehensive analysis showing room for future work.
We have observed significant progress in visual navigation for embodied agents. A common assumption in studying visual navigation is that the environments are static; this is a limiting assumption. Intelligent navigation may involve interacting with the environment beyond just moving forward/backward and turning left/right. Sometimes, the best way to navigate is to push something out of the way. In this paper, we study the problem of interactive navigation where agents learn to change the environment to navigate more efficiently to their goals. To this end, we introduce the Neural Interaction Engine (NIE) to explicitly predict the change in the environment caused by the agent's actions. By modeling the changes while planning, we find that agents exhibit significant improvements in their navigational capabilities. More specifically, we consider two downstream tasks in the physics-enabled, visually rich, AI2-THOR environment: (1) reaching a target while the path to the target is blocked (2) moving an object to a target location by pushing it. For both tasks, agents equipped with an NIE significantly outperform agents without the understanding of the effect of the actions indicating the benefits of our approach.
Recent observations have advanced our understanding of the neural network optimization landscape, revealing the existence of (1) paths of high accuracy containing diverse solutions and (2) wider minima offering improved performance. Previous methods observing diverse paths require multiple training runs. In contrast we aim to leverage both property (1) and (2) with a single method and in a single training run. With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks. These neural network subspaces contain diverse solutions that can be ensembled, approaching the ensemble performance of independently trained networks without the training cost. Moreover, using the subspace midpoint boosts accuracy, calibration, and robustness to label noise, outperforming Stochastic Weight Averaging.