Learning to recognize occluded and small objects with partial inputs
Recognizing multiple objects in an image is challenging due to occlusions, and becomes even more so when the objects are small. While promising, existing multi-label image recognition models do not explicitly learn context-based representations, and hence struggle to correctly recognize small and occluded objects. Intuitively, recognizing occluded objects requires knowledge of partial input, and hence context. Motivated by this intuition, we propose Masked Supervised Learning (MSL), a single-stage, model-agnostic learning paradigm for multi-label image recognition. The key idea is to learn context-based representations using a masked branch and to model label co-occurrence using label consistency. Experimental results demonstrate the simplicity, applicability and more importantly the competitive performance of MSL against previous state-of-the-art methods on standard multi-label image recognition benchmarks. In addition, we show that MSL is robust to random masking and demonstrate its effectiveness in recognizing non-masked objects. Code and pretrained models are available on GitHub.
Code (1)
Tasks
Multi-Label Image RecognitionSimilar Papers 제목 키워드 기반
Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion
Deep convolutional neural networks (DCNNs) are powerful models that yield impressive results at object classification. However, recent work has shown that they do not generalize well to partially occluded objects and to …
General Classificationimage-classificationImage ClassificationObjectCompositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion
Computer vision systems in real-world applications need to be robust to partial occlusion while also being explainable. In this work, we show that black-box deep convolutional neural networks (DCNNs) have only limited ro…
image-classificationImage Classificationobject-detectionObject Detection+1Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion
Recent findings show that deep convolutional neural networks (DCNNs) do not generalize well under partial occlusion. Inspired by the success of compositional models at classifying partially occluded objects, we propose t…
General ClassificationIncreasing CNN Robustness to Occlusions by Reducing Filter Support
Convolutional neural networks (CNNs) provide the current state of the art in visual object classification, but they are far less accurate when classifying partially occluded objects. A straightforward way to improve clas…
General ClassificationObjectRecurrent computations for visual pattern completion
Making inferences from partial information constitutes a critical aspect of cognition. During visual perception, pattern completion enables recognition of poorly visible or occluded objects. We combined psychophysics, ph…
Image Classification