Object-Level Context Modeling For Scene Classification with Context-CNN
arXiv:1705.04358
Abstract
Convolutional Neural Networks (CNNs) have been used extensively for computer vision tasks and produce rich feature representation for objects or parts of an image. But reasoning about scenes requires integration between the low-level feature representations and the high-level semantic information. We propose a deep network architecture which models the semantic context of scenes by capturing object-level information. We use Long Short Term Memory(LSTM) units in conjunction with object proposals to incorporate object-object relationship and object-scene relationship in an end-to-end trainable manner. We evaluate our model on the LSUN dataset and achieve results comparable to the state-of-art. We further show visualization of the learned features and analyze the model with experiments to verify our model's ability to model context.
Scene Understanding workshop (SUNw), CVPR 2017
References in corpus (13)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- VQA: Visual Question Answering
- CNN Features off-the-shelf: an Astounding Baseline for Recognition
- Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
- CNN-RNN: A Unified Framework for Multi-label Image Classification
- Training Deeper Convolutional Networks with Deep Supervision
- Locally-Supervised Deep Hybrid Model for Scene Recognition
- Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
- Semantic Object Parsing with Local-Global Long Short-Term Memory
- Fusing Multi-Stream Deep Networks for Video Classification
- Exploring Person Context and Local Scene Context for Object Detection
- Semantic Object Parsing with Graph LSTM