Unsupervised object detection using deep neural networks is typically a difficult problem with few to no guarantees about the learned representation. In this work we present the first unsupervised object detection method that is theoretically guaranteed to recover the true object positions up to quantifiable small shifts. We develop an unsupervised object detection architecture and prove that the learned variables correspond to the true object positions up to small shifts related to the encoder and decoder receptive field sizes, the object sizes, and the widths of the Gaussians used in the rendering process. We perform detailed analysis of how the error depends on each of these variables and perform synthetic experiments validating our theoretical predictions up to a precision of individual pixels. We also perform experiments on CLEVR-based data and show that, unlike current SOTA object detection methods (SAM, CutLER), our method's prediction errors always lie within our theoretical bounds. We hope that this work helps open up an avenue of research into object detection methods with theoretical guarantees.

This protocol is often regarded as a "golden compass" for navigating SoT A detectors. But can these stand-out "winners" be

This allows us to interpret the latent variables as object positions and lets us train the network without supervision.

We evaluate our method on three well-known model architectures:, i.e., SSD [ Named Entity Recognition, and Question Answering. Find more details in Table 5. Recall, ROC-AUC, and Average Scanning Overheads for each model. A value of 1 indicates perfect classification, while a value of 0.5 indicates To the best of our knowledge, there is no existing detection methods for object detection models. We evaluate the IoU threshold used to calculate the ASR of inverted triggers. However, a threshold of 0.7 tends to degrade the Different score thresholds are tested when computing the ASR of inverted triggers.