Andrew Gallagher

Yunhao Ge, Jie Ren, Andrew Gallagher et al. · deepmind

Multi-modal image-text models such as CLIP and LiT have demonstrated impressive performance on image classification benchmarks and their zero-shot generalization ability is particularly exciting. While the top-5 zero-shot accuracies of these models are very high, the top-1 accuracies are much lower (over 25% gap in some cases). We investigate the reasons for this performance gap and find that many of the failure cases are caused by ambiguity in the text prompts. First, we develop a simple and efficient zero-shot post-hoc method to identify images whose top-1 prediction is likely to be incorrect, by measuring consistency of the predictions w.r.t. multiple prompts and image transformations. We show that our procedure better predicts mistakes, outperforming the popular max logit baseline on selective prediction tasks. Next, we propose a simple and efficient way to improve accuracy on such uncertain images by making use of the WordNet hierarchy; specifically we augment the original class by incorporating its parent and children from the semantic label hierarchy, and plug the augmentation into text prompts. We conduct experiments on both CLIP and LiT models with five different ImageNet-based datasets. For CLIP, our method improves the top-1 accuracy by 17.13% on the uncertain subset and 3.6% on the entire ImageNet validation set. We also show that our method improves across ImageNet shifted datasets, four other datasets, and other model architectures such as LiT. The proposed method is hyperparameter-free, requires no additional model training and can be easily scaled to other large multi-modal architectures. Code is available at https://github.com/gyhandy/Hierarchy-CLIP.

Tyler R. Scott, Ting Liu, Michael C. Mozer et al.

Recent research in clustering face embeddings has found that unsupervised, shallow, heuristic-based methods -- including $k$-means and hierarchical agglomerative clustering -- underperform supervised, deep, inductive methods. While the reported improvements are indeed impressive, experiments are mostly limited to face datasets, where the clustered embeddings are highly discriminative or well-separated by class (Recall@1 above 90% and often nearing ceiling), and the experimental methodology seemingly favors the deep methods. We conduct a large-scale empirical study of 17 clustering methods across three datasets and obtain several robust findings. Notably, deep methods are surprisingly fragile for embeddings with more uncertainty, where they match or even perform worse than shallow, heuristic-based methods. When embeddings are highly discriminative, deep methods do outperform the baselines, consistent with past results, but the margin between methods is much smaller than previously reported. We believe our benchmarks broaden the scope of supervised clustering methods beyond the face domain and can serve as a foundation on which these methods could be improved. To enable reproducibility, we include all necessary details in the appendices, and plan to release the code.

Yunhao Ge, Jie Ren, Jiaping Zhao et al.

We focus on the challenge of out-of-distribution (OOD) detection in deep learning models, a crucial aspect in ensuring reliability. Despite considerable effort, the problem remains significantly challenging in deep learning models due to their propensity to output over-confident predictions for OOD inputs. We propose a novel one-class open-set OOD detector that leverages text-image pre-trained models in a zero-shot fashion and incorporates various descriptions of in-domain and OOD. Our approach is designed to detect anything not in-domain and offers the flexibility to detect a wide variety of OOD, defined via fine- or coarse-grained labels, or even in natural language. We evaluate our approach on challenging benchmarks including large-scale datasets containing fine-grained, semantically similar classes, distributionally shifted images, and multi-object images containing a mixture of in-domain and OOD objects. Our method shows superior performance over previous methods on all benchmarks. Code is available at https://github.com/gyhandy/One-Class-Anything

Tyler R. Scott, Andrew C. Gallagher, Michael C. Mozer

Recent work has argued that classification losses utilizing softmax cross-entropy are superior not only for fixed-set classification tasks, but also by outperforming losses developed specifically for open-set tasks including few-shot learning and retrieval. Softmax classifiers have been studied using different embedding geometries -- Euclidean, hyperbolic, and spherical -- and claims have been made about the superiority of one or another, but they have not been systematically compared with careful controls. We conduct an empirical investigation of embedding geometry on softmax losses for a variety of fixed-set classification and image retrieval tasks. An interesting property observed for the spherical losses lead us to propose a probabilistic classifier based on the von Mises-Fisher distribution, and we show that it is competitive with state-of-the-art methods while producing improved out-of-the-box calibration. We provide guidance regarding the trade-offs between losses and how to choose among them.

Amir Sadovnik, Wassim Gharbi, Thanh Vu et al.

Face images are one of the main areas of focus for computer vision, receiving on a wide variety of tasks. Although face recognition is probably the most widely researched, many other tasks such as kinship detection, facial expression classification and facial aging have been examined. In this work we propose the new, subjective task of quantifying perceived face similarity between a pair of faces. That is, we predict the perceived similarity between facial images, given that they are not of the same person. Although this task is clearly correlated with face recognition, it is different and therefore justifies a separate investigation. Humans often remark that two persons look alike, even in cases where the persons are not actually confused with one another. In addition, because face similarity is different than traditional image similarity, there are challenges in data collection and labeling, and dealing with diverging subjective opinions between human labelers. We present evidence that finding facial look-alikes and recognizing faces are two distinct tasks. We propose a new dataset for facial similarity and introduce the Lookalike network, directed towards similar face classification, which outperforms the ad hoc usage of a face recognition network directed at the same task.

Clint Solomon Mathialagan, Andrew C. Gallagher, Dhruv Batra

People preserve memories of events such as birthdays, weddings, or vacations by capturing photos, often depicting groups of people. Invariably, some individuals in the image are more important than others given the context of the event. This paper analyzes the concept of the importance of individuals in group photographs. We address two specific questions -- Given an image, who are the most important individuals in it? Given multiple images of a person, which image depicts the person in the most important role? We introduce a measure of importance of people in images and investigate the correlation between importance and visual saliency. We find that not only can we automatically predict the importance of people from purely visual cues, incorporating this predicted importance results in significant improvement in applications such as im2text (generating sentences that describe images of groups of people).